检索结果-内蒙古大学图书馆

24th International Arab Conference on Information Technology, ACIT 2023

作者： Alazaidah, Raed Hassan, Mohammad Al-Rbabah, Lara Samara, Ghassan Yusof, Marina Al-Sherideh, Ala'a Saeb Zarqa University Ai Faculty of Information Technology Department of Data Science Zarqa Jordan Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan The Hashemite University Faculty of Engineering Department of Computer Engineering Zarqa Jordan Selanger Malaysia Zarqa University Faculty of Information Technology Department of Cyber Security Zarqa Jordan

ISBN: (纸本)9798350384307

During the last few years, several real-life applications have attempted to utilize the proven high capabilities of artificial intelligence in general and machine learning in particular. Machine learning has been utilized in several domains, such as spam detection, image recognition, recommendation systems, self-driving cars, and medical diagnosis. This paper aims to survey the most related work of utilizing machine learning in the domain of medical diagnosis. Moreover, the paper proposes a comparative analysis for identifying and determining the best classification model and feature selection method in mind of handling medical datasets. Hence, four different medical datasets have been used to train twenty-three classification models and four well-known feature selection methods with respect to several evaluation metrics such as Accuracy, True Positive ratio, False Positive ratio, Precision, and Recall. The results reveal that RandomForest, J48, and SMO classifiers are the best classifiers when it comes to handling medical datasets respectively. Furthermore, the Gain Ratio method is the best choice for handling the step of feature selection. © 2023 IEEE.

关键词： Classification Feature Selection Machine Learning Medical Diagnosis Prediction

来源：评论

学校读者我要写书评

暂无评论

Diet Recommendation System for Human Health Using Machine Learning

Diet Recommendation System for Human Health Using Machine Le...

引用

International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS)

作者： B. VeerasekharReddy Venkata Nagaraju Thatha G. Uday Kiran Sk.Khaja Shareef N. V. RajaSekharReddy Yallapragada Ravi Raju Department of Information Technology MLR Institute of Technology Hyderabad India Department of Computer Science and Engineering (AI & ML) B V Raju Institute of Technology Narsapur Medak India Department of Computer Science and Engineering Madanapalli Institute of Technology Madanapalli India

In the past and present generation, the change in lifestyle of young people, less number of physical activities and eating fast food led to an alarming increase of diseases especially with college students. The unhealthy diet of students is responsible for unbalanced weight. The body mass index is used to classify a person's mass or weight as underweight, normal weight, over weight and obese based on tissue mass (bone, fat, and muscle) and height. Underweight leads to malnutrition, vitamin deficiencies, decrease in immune system function, growth issues and development issues. Major risk of being overweight leads to type-2 diabetes. Machine learning algorithms can solve many health problems. The project suggests the creation of an electronic college nurse that can perform the same functions as a human college nurse. This e-nurse will track students' health by utilizing BMI measurements, identify health issues like Type-2 diabetes by utilizing machine learning algorithms, and create a customized e-learning program that focuses on healthy habits such as regular exercise and a nutritious diet. These e-learning modules will be incorporated at appropriate intervals during the students' academic journey.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Preference detection of the humanoid robot face based on EEG and eye movement

引用

Neural Computing and Applications 2024年第19期36卷 11603-11621页

作者： Wang, Pengchao Mu, Wei Zhan, Gege Wang, aiping Song, Zuoting Fang, Tao Zhang, Xueze Wang, Junkongshuai Niu, Lan Bin, Jianxiong Zhang, Lihua Jia, Jie Kang, Xiaoyang Laboratory for Neural Interface and Brain Computer Interface Engineering Research Center of AI and Robotics Ministry of Education Shanghai Engineering Research Center of AI and Robotics MOE Frontiers Center for Brain Science State Key Laboratory of Medical Neurobiology Institute of AI and Robotics Academy for Engineering and Technology Fudan University Shanghai200433 China Ji Hua Laboratory Guangdong Province Foshan528200 China Department of Rehabilitation Medicine Huashan Hospital Fudan University Shanghai200040 China Yiwu Research Institute of Fudan University Zhejiang Yiwu322000 China Research Center for Intelligent Sensing Zhejiang Lab Hangzhou311121 China

The face of a humanoid robot can affect the user experience, and the detection of face preference is particularly important. Preference detection belongs to a branch of emotion recognition that has received much attention from researchers. Most of the previous preference detection studies have been conducted based on a single modality. In this paper, we detect face preferences of humanoid robots based on electroencephalogram (EEG) signals and eye movement signals for single modality, canonical correlation analysis fusion modality, and bimodal deep autoencoder (BDAE) fusion modality, respectively. We validated the theory of frontal asymmetry by analyzing the preference patterns of EEG and found that participants had higher alpha wave energy for preference faces. In addition, hidden preferences extracted by EEG signals were better classified than preferences from participants' subjective feedback, and also, the classification performance of eye movement data was improved. Finally, experimental results showed that BDAE multimodal fusion using frontal alpha and beta power spectral densities and eye movement information as features performed best, with the highest average accuracy of 83.13% for the SVM and 71.09% for the KNN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Acoustic Based Bird Species Classification Using Deep Learning

Acoustic Based Bird Species Classification Using Deep Learni...

引用

Information Technology, Electronics and Intelligent Communication Systems (ICITEICS), IEEE International Conference on

作者： Lade Gunakar Rao K Sridhar Sallauddin Mohmmad Bhargav Somisetty Rashmi Shivanadhuni School of Computer Science and Artificaial Intelligence SR University Warangal Telangana India Vaageswari College of Engineering Thimmapur Karimnager Telangana India Department of CSE(AI&ML) CVR College of Engineering Hyderabad Telangana India Computer Science and Engineering Malla Reddy Institute of Technology and Science Hyderabad Telangana

ISBN: (数字)9798350382693

ISBN: (纸本)9798350382709

This paper uses deep learning techniques to present a novel approach for acoustic-based bird species classification. Leveraging a dataset comprising 10,955 audio samples from six distinct bird species, we extracted diverse features, including chroma, spectrogram, and MFCCs. These features were stacked to form input tensors of size 48x128x1, subsequently fed into a CNN architecture. Our model achieved a commendable accuracy of 0.81 in classifying bird species, demonstrating the efficacy of the proposed methodology. This research contributes to bioacoustics and avian ecology by offering a reliable tool for automated bird species identification, which holds promise for various applications, including biodiversity monitoring and conservation efforts.

关键词： Deep learning Tensors Communication systems Birds Feature extraction Ecology Reliability

来源：评论

学校读者我要写书评

暂无评论

Puzzle Progression Game Using Reinforcement Learning

Puzzle Progression Game Using Reinforcement Learning

引用

Smart Technologies for Sustainable Development Goals (ICSTSDG), International Conference on

作者： Abhigyan Ghoshal Mohammad Armaan Ali Kumaran K CSE(AI&ML) Vellore Institute of Technology Chennai campus India School of Computer Science and Engineering (SCOPE) Vellore Institute of Technology Chennai campus India

ISBN: (数字)9798331516284

ISBN: (纸本)9798331516291

This paper presents an innovative approach to puzzle progression games by integrating reinforcement learning (RL), specifically Q-learning, to dynamically adjust the puzzle difficulty and enhance the player experience. Unlike traditional puzzle games, which employ manually designed levels with fixed difficulty curves, this system utilizes RL to create an evolving challenge tailored to the player's skill level. The RL agent, trained through trial and error, progressively learns optimal strategies for solving increasingly complex puzzles without requiring a predefined model of the environment. Experimental results demonstrate that RL-based agents outperform traditional rule-based systems in terms of adaptability, efficiency, and scalability. The paper also explores potential future developments, including hybrid models that integrate deep learning with RL to tackle more complex puzzles and the possibility of multi-agent environments. The work highlights the benefits of RL in revolutionizing game design, providing dynamic, player-responsive experiences.

关键词： Deep learning Adaptation models Q-learning Scalability Games Complexity theory Sustainable development

来源：评论

学校读者我要写书评

暂无评论

A Transfer Learning Based Web App for Glaucoma Detection Using Low-Cost Ophthalmoscopic Camera

A Transfer Learning Based Web App for Glaucoma Detection Usi...

引用

Network, Multimedia and Information Technology (NMITCON) International Conference on

作者： B K Chethan Sanjana Vishwanath Sambargi D Roopashree K Prabhavathi Kiran Puttegowda D S Sunil Kumar Department of Computer Science Engineering (AI&ML) Vidyavardhaka College of Engineering Mysuru India Department of AI and ML Coorg Institute Of Technology Ponnampet Karnataka India Department of ECE Government Engineering College Hassan Karnataka India Department of ECE BGS Institute of Technology Adichunchanagiri University Mandya Karnataka India Department of ECE Vidyavardhaka College of Engineering Mysuru Karnataka India Anatta innovations BGS B-School Bengaluru India

ISBN: (数字)9798350372892

ISBN: (纸本)9798350372908

Glaucoma has been the most fundamental cause of irreversible blindness in persons over a few decades. This condition is extremely prevalent in several nations, and in the worst-case situation is that many countries do not have enough ophthalmologists. According to data from global glaucoma research, roughly 12 million individuals would be symbiotically blind from early-stage glaucoma by 2020. To evaluate the disease in the eye, fundus photography is used. Fundus photos require a lengthy visual inspection. The transfer-learning based web-app for glaucoma detection utilizing low-cost ophthalmoscopic cameras is presented in this paper. Fundus evaluation is an important part of an eye exam that helps the web-app provide vital diagnostic information to both ophthalmologists and non-ophthalmologists. Vision impairment occurs over time because it is not a rapid consequence. Only in the later stages those signs are noticed. The optic nerve was studied using 2-Dimensional retinal fundus pictures, which is a difficult task that can result in a significant cost for detecting regular glaucoma. There are a variety of different tests that can be used to rule out glaucoma, including tonometry which signifies pressure on eye, gonioscopy which examines angle is closed or open, OCT - Optical Coherence Tomography, Ophthalmoscopic Imaging to visualize retina as well as optic nerve and Fundus Copying. In this paper, an effective embedded based eye testing architecture is presented.

关键词： Glaucoma Performance evaluation Biomedical optical imaging Transfer learning Medical services Cameras Retina Optical imaging Adaptive optics Servers

来源：评论

学校读者我要写书评

暂无评论

Learning against Non-credible Second-Price Auctions 25

Learning against Non-credible Second-Price Auctions

引用

34th ACM Web Conference, WWW 2025

作者： Wang, Qian Xia, Xuanzhi Yang, Zongjun Deng, Xiaotie Kong, Yuqing Zhang, Zhilin Wang, Liang Yu, Chuan Xu, Jian Zheng, Bo CFCS School of Computer Science Peking University Beijing China Alibaba Group Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Department of Industrial Engineering and Operations Research Columbia University New York United States CMAR Institute for AI Peking University Beijing China

ISBN: (纸本)9798400712746

The standard framework of online bidding algorithm design assumes that the seller commits himself to faithfully implementing the rules of the adopted auction. However, the seller may attempt to cheat in execution to increase his revenue if the auction belongs to the class of non-credible auctions. For example, in a second-price auction, the seller could create a fake bid between the highest bid and the second highest bid. This paper focuses on one such case of online bidding in repeated second-price auctions. At each time t, the winner with bid bt is charged not the highest competing bid dt but a manipulated price pt = α0dt + (1 − α0)bt, where the parameter α0 ∈ [0, 1] in essence measures the seller’s credibility. Unlike classic repeated-auction settings where the bidder has access to samples (ds)st=−11, she can only receive mixed signals of (bs)st=−11, (ds)st=−11 and α0 in this problem. The task for the bidder is to learn not only the bid distributions of her competitors but also the seller’s credibility. We establish regret lower bounds in various information models and provide corresponding online bidding algorithms that can achieve near-optimal performance. Specifically, we consider three cases of prior information based on whether the credibility α0 and the distribution of the highest competing bids are known. Our goal is to characterize the landscape of online bidding in non-credible second-price auctions and understand the impact of the seller’s credibility on online bidding algorithm design under different information structures. © 2025 Copyright held by the owner/author(s).

关键词： bidding algorithms

来源：评论

学校读者我要写书评

暂无评论

Fusion of Convolutional Neural Networks and Random Forests for Accurate Potato Leaf Disease Detection

Fusion of Convolutional Neural Networks and Random Forests f...

引用

Applied Intelligence and Computing (aiC), IEEE World Conference on

作者： Durgunala Ranjith Bhargav Somisetty Sallauddin Mohmmad P Ramana Jayapal Lande School of Computer Science and Artificaial Intelligence SR University Warangal Telangana India Department of CSE(AI&ML) CVR College of Engineerning Hyderabad Telangana India Computer Science and Engineering Hyderabad Institute of Technology and Management Hyderabad Telangana India

ISBN: (数字)9798350384598

ISBN: (纸本)9798350384604

In order to classify potato leaf diseases, this work suggests a hybrid model that combines a Random Forest classifier for sample class classification with a CNN for image feature extraction. The dataset obtained from Kaggle includes 1885 samples of different potato leaf illnesses caused by fungi, viruses, pests, bacteria, Phytophthora, nematodes, and healthy leaves. Thorough preprocessing entails dividing the dataset into equal training, testing, and validation sets and downsizing photos to a standard dimension. The CNN model uses ReLU activation for normalization and softmax activation for classification. It has five layers with progressively larger filter sizes. For the final label classification, features taken from the CNN are fed into a Random Forest classifier consisting of 100 decision trees. The suggested model shows promise in terms of performance and accuracy in classifying diseases. The hybrid model suggested for classifying diseases affecting potatoes shows encouraging results; it has an overall accuracy rate of 77% and a precision range of 44% to 96% for various disease categories.

关键词： Training Accuracy Computational modeling Crops Convolutional neural networks Random forests Standards Optimization Diseases Testing

来源：评论

学校读者我要写书评

暂无评论

Mitigating Spurious Correlation in Natural Language Understanding with Counterfactual Inference

Mitigating Spurious Correlation in Natural Language Understa...

引用

2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022

作者： Udomcharoenchaikit, Can Ponwitayarat, Wuttikorn Payoungkhamdee, Patomporn Masuk, Kanruethai Buaphet, Weerayut Chuangsuwanich, Ekapol Nutanong, Sarana School of Information Science and Technology VISTEC Thailand VISAI AI Thailand Department of Computer Engineering Chulalongkorn University Thailand

Despite their promising results on standard benchmarks, NLU models are still prone to make predictions based on shortcuts caused by unintended bias in the dataset. For example, an NLI model may use lexical overlap as a shortcut to make entailment predictions due to repetitive data generation patterns from annotators, also called annotation artifacts. In this paper, we propose a causal analysis framework to help debias NLU models. We show that (1) by defining causal relationships, we can introspect how much annotation artifacts affect the outcomes. (2) We can utilize counterfactual inference to mitigate bias with this knowledge. We found that viewing a model as a treatment can mitigate bias more effectively than viewing annotation artifacts as treatment. (3) In addition to bias mitigation, we can interpret how much each debiasing strategy is affected by annotation artifacts. Our experimental results show that using counterfactual inference can improve out-of-distribution performance in all settings while maintaining high in-distribution performance. © 2022 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Effective Security Protocol Design for IRIS based Credential Evaluation using Intensive Deep Learning Scheme 2

An Effective Security Protocol Design for IRIS based Credent...

引用

2nd IEEE International Conference on Advances in Computing, Communication and Applied Informatics, ACCai 2023

作者： Ramachandran, R. Hema Priya, K. Malathy, K. Sivagamidevi, G. Sudhakar, C. Venkata Indhumathi, V. Rajalakshmi Engineering College Department of Biomedical Engineering Chennai India Easwari Engineering College Department of Computer Science and Engineering Chennai India S.A. Engineering College Department of Master of Computer Applications Chennai India Dhanalakshmi College of Engineering Dept of Ai & Ds Chennai India SreeVidyanikethan Engineering College Department of ECE Andhra Pradesh Tirupati India Panimalar Institute of Technology Department of It Chennai India

ISBN: (纸本)9798350315905

The component of a system charged with ensuring the security of its users is among its most crucial parts. It has been demonstrated that using a password or login that is too basic makes you vulnerable to hackers and does not ensure a high level of security. Authentication using biometric methods can be achieved in several ways. Some of the most advanced and reliable are facial recognition technology and iris recognition. Because it relies heavily on detection of patterns, it is able to reliably identify the rightful owner of an Iris scan. Accuracy as well as effectiveness have both been greatly enhanced in the resultant recognition system. Security breaches and other identification scams are on the rise, making it all the more crucial to implement a robust biometric system. The option that has gained a lot of attention is biometric identification. The iris's potential as a biometric has gained traction in recent years. This quantifiable quality ensures great productivity and precision, which is what triggered the phenomenon. We present a complete ResNet50-based deep learning system for iris identification in this study. Utilizing only a small number of training photos from every class, we train our algorithm on a popular identification of iris dataset, achieving significant gains over prior methods. In addition, we introduce a visualization method that may identify key features of iris pictures that have a significant bearing on the precision of recognition. We anticipate that this approach will be utilized extensively in the future to improve the scalability and precision of various biometrics identification jobs © 2023 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：